mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Add visualization of bbox on page with html export.

Browse Source 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
This commit is contained in:
Peter Staar 2025-05-27 05:41:51 +02:00
parent 2579d89510
commit c9735de4c6
3 changed files with 678 additions and 114 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
docling/cli/main.py
View File

@ -12,6 +12,12 @@ from typing import Annotated, Dict, List, Optional, Type
import rich.table import rich.table
import typer import typer
from docling_core.transforms.serializer.html import (
HTMLDocSerializer,
HTMLOutputStyle,
HTMLParams,
)
from docling_core.transforms.visualizer.layout_visualizer import LayoutVisualizer
from docling_core.types.doc import ImageRefMode from docling_core.types.doc import ImageRefMode
from docling_core.utils.file import resolve_source_to_path from docling_core.utils.file import resolve_source_to_path
from pydantic import TypeAdapter from pydantic import TypeAdapter
@ -156,6 +162,7 @@ def export_documents(
export_json: bool, export_json: bool,
export_html: bool, export_html: bool,
export_html_split_page: bool, export_html_split_page: bool,
# export_html_localization: bool,
export_md: bool, export_md: bool,
export_txt: bool, export_txt: bool,
export_doctags: bool, export_doctags: bool,
@ -189,9 +196,23 @@ def export_documents(
if export_html_split_page: if export_html_split_page:
fname = output_dir / f"{doc_filename}.html" fname = output_dir / f"{doc_filename}.html"
_log.info(f"writing HTML output to {fname}") _log.info(f"writing HTML output to {fname}")
"""
conv_res.document.save_as_html( conv_res.document.save_as_html(
filename=fname, image_mode=image_export_mode, split_page_view=True filename=fname, image_mode=image_export_mode, split_page_view=True
) )
"""
ser = HTMLDocSerializer(
doc=conv_res.document,
params=HTMLParams(
image_mode=image_export_mode,
output_style=HTMLOutputStyle.SPLIT_PAGE,
),
)
ser_res = ser.serialize(
visualizer=LayoutVisualizer(),
)
with open(fname, "w") as fw:
fw.write(ser_res.text)
# Export Text format: # Export Text format:
if export_txt: if export_txt:

769
poetry.lock generated
View File

File diff suppressed because it is too large Load Diff

2
pyproject.toml
View File

@ -46,7 +46,7 @@ packages = [{ include = "docling" }]
###################### ######################
python = "^3.9" python = "^3.9"
pydantic = "^2.0.0" pydantic = "^2.0.0"
docling-core = {version = "^2.29.0", extras = ["chunking"]} docling-core = "^2.31.2"
docling-ibm-models = "^3.4.0" docling-ibm-models = "^3.4.0"
docling-parse = "^4.0.0" docling-parse = "^4.0.0"
filetype = "^1.2.0" filetype = "^1.2.0"